Dispatching Parallel Agents

Overview

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Core principle: Dispatch one delegate per independent problem domain. Let them work concurrently.

When to Use

digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single delegate investigates all" [shape=box];
    "One delegate per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential delegates" [shape=box];
    "Parallel dispatch" [shape=box];

    "Multiple failures?" -> "Are they independent?" [label="yes"];
    "Are they independent?" -> "Single delegate investigates all" [label="no - related"];
    "Are they independent?" -> "Can they work in parallel?" [label="yes"];
    "Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
    "Can they work in parallel?" -> "Sequential delegates" [label="no - shared state"];
}

Use when:

• 3+ test files failing with different root causes
• Multiple subsystems broken independently
• Each problem can be understood without context from others
• No shared state between investigations

Don't use when:

• Failures are related (fix one might fix others)
• Need to understand full system state
• Delegates would interfere with each other

Pre-dispatch checklist: Before dispatching, scan the task list for operations subagents can't perform:

• File deletions → handle with git rm yourself
• Web search / AWS CLI calls → gather data yourself, include in briefing
• grep / glob searches → run yourself, pass results to subagent Extract these into a pre-dispatch step. Then dispatch the remaining tasks.

The Pattern

1. Identify Independent Domains

Group failures by what's broken:

• File A tests: Tool approval flow
• File B tests: Batch completion behavior
• File C tests: Abort functionality

Each domain is independent - fixing tool approval doesn't affect abort tests.

2. Create Focused Delegate Tasks

Each delegate gets:

• Specific scope: One test file or subsystem
• Clear goal: Make these tests pass
• Constraints: Don't change other code
• Expected output: Summary of what you found and fixed

3. Dispatch in Parallel

Use the delegate tool to launch all tasks concurrently:

Delegate 1 → "Fix agent-tool-abort.test.ts failures"
Delegate 2 → "Fix batch-completion-behavior.test.ts failures"
Delegate 3 → "Fix tool-approval-race-conditions.test.ts failures"

All three run concurrently.

4. Review and Integrate

When delegates return:

• Read each summary
• Verify fixes don't conflict
• Run full test suite
• Integrate all changes

Delegate Prompt Structure

Good delegate prompts are:

1. Focused - One clear problem domain
2. Self-contained - All context needed to understand the problem
3. Specific about output - What should the delegate return?

Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:

1. "should abort tool with partial output capture" - expects 'interrupted at' in message
2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
3. "should properly track pendingToolCount" - expects 3 results but gets 0

These are timing/race condition issues. Your task:

1. Read the test file and understand what each test verifies
2. Identify root cause - timing issues or actual bugs?
3. Fix by:
   - Replacing arbitrary timeouts with event-based waiting
   - Fixing bugs in abort implementation if found
   - Adjusting test expectations if testing changed behavior

Do NOT just increase timeouts - find the real issue.

Return: Summary of what you found and what you fixed.

Common Mistakes

Too broad: "Fix all the tests" - delegate gets lost Specific: "Fix agent-tool-abort.test.ts" - focused scope

No context: "Fix the race condition" - delegate doesn't know where Context: Paste the error messages and test names

No constraints: Delegate might refactor everything Constraints: "Do NOT change production code" or "Fix tests only"

Vague output: "Fix it" - you don't know what changed Specific: "Return summary of root cause and changes"

When NOT to Use

Related failures: Fixing one might fix others - investigate together first Need full context: Understanding requires seeing entire system Exploratory debugging: You don't know what's broken yet Shared state: Delegates would interfere (editing same files, using same resources)

Real Example from Session

Scenario: 6 test failures across 3 files after major refactoring

Failures:

• agent-tool-abort.test.ts: 3 failures (timing issues)
• batch-completion-behavior.test.ts: 2 failures (tools not executing)
• tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)

Decision: Independent domains - abort logic separate from batch completion separate from race conditions

Dispatch:

Delegate 1 → Fix agent-tool-abort.test.ts
Delegate 2 → Fix batch-completion-behavior.test.ts
Delegate 3 → Fix tool-approval-race-conditions.test.ts

Results:

• Delegate 1: Replaced timeouts with event-based waiting
• Delegate 2: Fixed event structure bug (threadId in wrong place)
• Delegate 3: Added wait for async tool execution to complete

Integration: All fixes independent, no conflicts, full suite green

Time saved: 3 problems solved in parallel vs sequentially

Key Benefits

1. Parallelization - Multiple investigations happen simultaneously
2. Focus - Each delegate has narrow scope, less context to track
3. Independence - Delegates don't interfere with each other
4. Speed - 3 problems solved in time of 1

Verification

After delegates return:

1. Review each summary - Understand what changed
2. Check for conflicts - Did delegates edit same code?
3. Run full suite - Verify all fixes work together
4. Spot check - Delegates can make systematic errors

Real-World Impact

From debugging sessions:

• 6 failures across 3 files
• 3 delegates dispatched in parallel
• All investigations completed concurrently
• All fixes integrated successfully
• Zero conflicts between delegate changes